I've reproduced these issues on a single-core machine which doesn't appear to become completely unresponsive after 12 hours of copying (as the other machines are deadlocking after 5-10 minutes, perhaps?), but it does use 100% SYS CPU with no IO traffic for the vast majority of the time. (In fact, constantly?) The filesystem was originally created on an Ubuntu Saucy 13.10 machine (and therefore older kernel + older btrfs-tools) on a PV guest with a non-SSD block device. The newer current machine is a HVM guest and the data is now on an SSD. Below is a link to the dstat output and dmesg which shows this (note the sys column on the left and the IOPs column on the right). This was taken whilst copying files of varying sizes from many directories to a sibling in the same directory. `dstat -tcdnymlr 5`, which shows high sys CPU but no IO traffic: https://gist.github.com/pwaller/cb8d088ebceb2707d24b INFO: task sync:5906 blocked for more than 120 seconds. https://gist.github.com/pwaller/574a369ea4b65fe125b9#file-dmesg-log-L541 INFO: task btrfs-transacti:2531 blocked for more than 120 seconds. https://gist.github.com/pwaller/574a369ea4b65fe125b9#file-dmesg-log-L1015 INFO: task btrfs-flush_del:16764 blocked for more than 120 seconds. https://gist.github.com/pwaller/574a369ea4b65fe125b9#file-dmesg-log-L1041 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
